You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/features/image-generation.md
+45-10Lines changed: 45 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,19 +1,24 @@
1
1
---
2
-
description: Generate images from text prompts directly in Roo Code using OpenRouter API. Save AI-generated images to your workspace with preview support.
2
+
description: Generate new images from text prompts or edit existing images in Roo Code using OpenRouter API. Transform, enhance, and save AI-processed images to your workspace with preview support.
3
3
keywords:
4
4
- image generation
5
+
- image editing
5
6
- text to image
7
+
- image transformation
6
8
- OpenRouter
7
9
- AI images
8
10
- experimental feature
9
11
- image creation
10
12
- prompt to image
13
+
- watercolor
14
+
- upscaling
15
+
- style transfer
11
16
image: /img/social-share.jpg
12
17
---
13
18
14
19
# Image Generation
15
20
16
-
Generate images from plain text prompts, save them to your project, and preview them in the chat. This experimental feature requires an OpenRouter API key.
21
+
Generate new images from text prompts or edit existing images in your workspace. Save results to your project with preview in chat. This experimental feature requires an OpenRouter API key.
17
22
18
23
:::warning Experimental Feature
19
24
Image Generation is an experimental feature that requires enabling in settings and configuring an OpenRouter API key.
@@ -23,25 +28,32 @@ Image Generation is an experimental feature that requires enabling in settings a
23
28
24
29
## Key Features
25
30
26
-
- Create images directly from chat using natural language
27
-
- Saves to your workspace at a path you choose; file extension is auto-added if missing
28
-
- Shows a preview of the generated image in the conversation
29
-
- Choose an image generation model (via OpenRouter)
31
+
- Create new images from text prompts using natural language
32
+
- Edit and transform existing images in your workspace
33
+
- Saves to your workspace at a path you choose; appropriate extension (.png or .jpg) is auto-added if missing
34
+
- Shows a preview of the generated/edited image in the conversation
35
+
- Currently uses Gemini 2.5 Flash Image Preview models via OpenRouter
30
36
- Simple on/off toggle under Experimental settings
31
37
32
38
---
33
39
34
-
## Use Case
40
+
## Use Cases
35
41
42
+
### Image Generation
36
43
**Before:** You had to copy prompts to an external site, download the result, then move it into your workspace.
37
44
38
45
**With this feature:** Ask Roo to generate an image, approve, pick a save location, and continue editing with the image already in your project.
39
46
47
+
### Image Editing
48
+
**Before:** Export image, upload to external editor, make changes, download, import back to project.
49
+
50
+
**With this feature:** Ask Roo to transform your existing image directly - it reads the file, applies your edits, and saves the result in your project.
51
+
40
52
---
41
53
42
54
## How It Works
43
55
44
-
When enabled, Roo sends your prompt to an image-capable model through OpenRouter. The image returned by OpenRouter is saved to the path you specify inside your current workspace. Roo shows a preview in the chat and the file appears in your file explorer.
56
+
When enabled, Roo sends your prompt (and optionally an existing image) to an image-capable model through OpenRouter. The generated or edited image returned by OpenRouter is saved to the path you specify inside your current workspace. Roo shows a preview in the chat and the file appears in your file explorer.
45
57
46
58
---
47
59
@@ -67,19 +79,39 @@ When enabled, Roo sends your prompt to an image-capable model through OpenRouter
67
79
68
80
### 3. Image Generation Model
69
81
-**Purpose:** Selects which model to use for generation
-**Available Models:** Currently limited to Gemini 2.5 Flash Image Preview and its free variant
71
84
72
85
---
73
86
74
87
## Using Image Generation
75
88
76
89
1. In chat, ask Roo to generate an image and describe what you want (subject, style, lighting, composition).
77
90
2. Confirm the action when prompted. Roo may ask you to choose a save path (for example: `images/sunset.png`).
78
-
3. Roo generates the image and saves it. If you don't include an extension, one is added automatically (png or jpg).
91
+
3. Roo generates the image and saves it. If you don't include an extension, the appropriate extension (.png or .jpg) is added based on the output format.
79
92
4. See the image preview in the chat and locate the file in your workspace.
80
93
81
94
---
82
95
96
+
## Editing Existing Images
97
+
98
+
Roo can also transform and edit existing images in your workspace:
99
+
100
+
1. Ask Roo to edit an image, describing the transformation you want
101
+
2. Specify both the input image path and where to save the result
102
+
3. Roo will apply your requested edits to the existing image
description: This release adds image editing capabilities to the image generation tool and improves developer experience.
3
+
keywords:
4
+
- roo code 3.26.3
5
+
- image editing
6
+
- image generation
7
+
image: /img/social-share.jpg
8
+
---
9
+
10
+
# Roo Code 3.26.3 Release Notes (2025-08-29)
11
+
12
+
This release adds image editing capabilities to the image generation tool and improves developer experience.
13
+
14
+
## Image Editing with Input Images
15
+
16
+
We've enhanced the image generation tool with the ability to edit and transform existing images ([#7525](https://github.com/RooCodeInc/Roo-Code/pull/7525)):
17
+
18
+
-**Transform Existing Images**: Apply artistic styles, convert photos to paintings, or create variations of existing artwork
19
+
-**Style Transfer**: Convert images into watercolor, oil painting, sketch, or other artistic styles
20
+
-**Image Enhancement**: Upscale and enhance existing images to higher resolution while maintaining composition
21
+
-**Creative Editing**: Use text prompts to modify specific aspects of an image while preserving the rest
22
+
23
+
The tool now accepts an optional `image` parameter for transforming existing images in your workspace. Supported input formats include PNG, JPG, JPEG, GIF, and WEBP.
24
+
25
+
> **📚 Documentation**: See [Image Generation - Editing Existing Images](/features/image-generation#editing-existing-images) for detailed usage and transformation examples.
26
+
27
+
## Bug Fixes
28
+
29
+
***Image Generation Settings**: Fixed issue where the saved API key would clear when switching modes ([#7536](https://github.com/RooCodeInc/Roo-Code/pull/7536))
30
+
31
+
## Misc Improvements
32
+
33
+
***Test Debugging**: Console logs now visible in tests when using the --no-silent flag (thanks hassoncs!) ([#7467](https://github.com/RooCodeInc/Roo-Code/pull/7467))
Generate images from natural‑language prompts directly inside Roo Code using OpenRouter’s image generation models. Configure your OpenRouter API key, pick a supported model, and preview results in the built‑in Image Viewer. See [Image Generation](/features/image-generation) and [OpenRouter Provider](/providers/openrouter) for setup and model selection.
72
+
Generate images from natural‑language prompts directly inside Roo Code using OpenRouter's image generation models. Configure your OpenRouter API key, pick a supported model, and preview results in the built‑in Image Viewer. See [Image Generation](/features/image-generation) and [OpenRouter Provider](/providers/openrouter) for setup and model selection.
73
73
74
74
-**Free option available: Gemini 2.5 Flash Image Preview** — try image generation without paid credits for faster onboarding and quick experiments
75
75
- Prompt‑to‑image workflow inside the editor with approvals flow (supports auto‑approval when write permissions are granted)
76
76
- Image Viewer with zoom, copy, and save for quick reuse in docs and prototypes
77
+
-**NEW in v3.26.3: Image Editing** — Transform and edit existing images in your workspace ([#7525](https://github.com/RooCodeInc/Roo-Code/pull/7525)):
78
+
- Apply artistic styles like watercolor, oil painting, or sketch
79
+
- Upscale and enhance images to higher resolution
80
+
- Modify specific aspects while preserving the rest
81
+
- Supports PNG, JPG, JPEG, GIF, and WEBP input formats
***Mistral Thinking Content**: Fixed validation errors when using Mistral models that send thinking content (thanks Biotrioo!) ([#7106](https://github.com/RooCodeInc/Roo-Code/pull/7106))
107
114
***Requesty Model Listing**: Fixed model listing for Requesty provider when using custom base URLs (thanks dtrugman!) ([#7378](https://github.com/RooCodeInc/Roo-Code/pull/7378))
108
115
***Todo List Setting**: Fixed newTaskRequireTodos setting to properly enforce todo list requirements ([#7363](https://github.com/RooCodeInc/Roo-Code/pull/7363))
116
+
***Image Generation Settings** (v3.26.3): Fixed issue where the saved API key would clear when switching modes ([#7536](https://github.com/RooCodeInc/Roo-Code/pull/7536))
109
117
* ImageGenerationSettings no longer shows a dirty state on first open; the save button only enables after an actual change. (#[7495](https://github.com/RooCodeInc/Roo-Code/pull/7495))
110
118
* GPT‑5 reliability improvements:
111
119
- Manual condense preserves conversation continuity by correctly handling `previous_response_id` on the next request
***Issue Fixer Mode**: Added missing todos parameter in new_task tool usage ([#7391](https://github.com/RooCodeInc/Roo-Code/pull/7391))
129
137
***Privacy Policy Update**: Updated privacy policy to clarify proxy mode data handling (thanks jdilla1277!) ([#7255](https://github.com/RooCodeInc/Roo-Code/pull/7255))
130
138
***Dependencies**: Updated drizzle-kit to v0.31.4 ([#5453](https://github.com/RooCodeInc/Roo-Code/pull/5453))
139
+
***Test Debugging** (v3.26.3): Console logs now visible in tests when using the --no-silent flag (thanks hassoncs!) ([#7467](https://github.com/RooCodeInc/Roo-Code/pull/7467))
131
140
* Release automation: version bumps, changelog updates, and auto-publishing on merge for a faster, more reliable release process. (#[7490](https://github.com/RooCodeInc/Roo-Code/pull/7490))
132
141
* New TaskSpawned developer event so integrations can detect when a subtask is created and capture its ID for chaining or monitoring. (#[7465](https://github.com/RooCodeInc/Roo-Code/pull/7465))
133
142
* Roo Code Cloud SDK bumped to 0.25.0. (#[7475](https://github.com/RooCodeInc/Roo-Code/pull/7475))
134
143
* Release automation: version bumps, changelog updates, and auto-publishing on merge for a faster, more reliable release process. (#[7490](https://github.com/RooCodeInc/Roo-Code/pull/7490))
135
144
* New TaskSpawned developer event so integrations can detect when a subtask is created and capture its ID for chaining or monitoring. (#[7465](https://github.com/RooCodeInc/Roo-Code/pull/7465))
145
+
136
146
* Roo Code Cloud SDK bumped to 0.25.0. (#[7475](https://github.com/RooCodeInc/Roo-Code/pull/7475))
0 commit comments